English
Related papers

Related papers: Back to Ear: Perceptually Driven High Fidelity Mus…

200 papers

While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-02 Zhikang Niu , Shujie Hu , Jeongsoo Choi , Yushen Chen , Peining Chen , Pengcheng Zhu , Yunting Yang , Bowen Zhang , Jian Zhao , Chunhui Wang , Xie Chen

Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics…

Machine Learning · Computer Science 2021-10-28 Naoya Takeishi , Alexandros Kalousis

We present a comparative evaluation of latent space organization in three Variational Autoencoders (VAEs) for musical timbre generation: an unsupervised VAE, a descriptor-conditioned VAE, and a VAE conditioned on continuous perceptual…

Sound · Computer Science 2026-03-18 Joseph Cameron , Alan Blackwell

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the…

Machine Learning · Computer Science 2020-04-20 Da Tang , Dawen Liang , Tony Jebara , Nicholas Ruozzi

Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf (2020)…

Machine Learning · Computer Science 2022-05-19 Frederic Koehler , Viraj Mehta , Chenghui Zhou , Andrej Risteski

This paper introduces the Procedural (audio) Variational autoEncoder (ProVE) framework as a general approach to learning Procedural Audio PA models of environmental sounds with an improvement to the realism of the synthesis while…

Sound · Computer Science 2023-03-07 Danzel Serrano , Mark Cartwright

Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to…

Sound · Computer Science 2022-12-21 Shih-Lun Wu , Yi-Hsuan Yang

Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…

Machine Learning · Statistics 2026-04-02 Veranika Boukun , Jörg Lücke

Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve efficiency via latent-space processing, their Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Yidi Liu , Xueyang Fu , Jie Huang , Jie Xiao , Dong Li , Wenlong Zhang , Lei Bai , Zheng-Jun Zha

Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error from variational autoencoder (VAE) via maximizing…

Machine Learning · Computer Science 2020-05-08 Seonho Park , George Adosoglou , Panos M. Pardalos

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…

Machine Learning · Computer Science 2026-02-20 Linwei Zhai , Han Ding , Mingzhi Lin , Cui Zhao , Fei Wang , Ge Wang , Wang Zhi , Wei Xi

Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful representation learning framework that can discover discrete groups of features from a speech signal without supervision. Until now, the VQ-VAE architecture has previously…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yi Zhao , Haoyu Li , Cheng-I Lai , Jennifer Williams , Erica Cooper , Junichi Yamagishi

Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiarui Guan , Wenshuai Zhao , Zhengtao Zou , Juho Kannala , Arno Solin

The combination of machine learning models with physical models is a recent research path to learn robust data representations. In this paper, we introduce p$^3$VAE, a variational autoencoder that integrates prior physical knowledge about…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Romain Thoreau , Laurent Risser , Véronique Achard , Béatrice Berthelot , Xavier Briottet

Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Hangyu Liu , Jianyong Wang , Yutao Sun

Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks. While it has been demonstrated that VAE training can suffer from a number of pathologies, existing literature…

Machine Learning · Statistics 2022-03-17 Yaniv Yacoby , Weiwei Pan , Finale Doshi-Velez

In recent years, neural network based methods have been proposed as a method that cangenerate representations from music, but they are not human readable and hardly analyzable oreditable by a human. To address this issue, we propose a novel…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-29 Jinsung Kim , Yeong-Seok Jeong , Woosung Choi , Jaehwa Chung , Soonyoung Jung

Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expressive decoders,…

Computation and Language · Computer Science 2021-11-25 Seongmin Park , Jihwa Lee

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Machine Learning · Computer Science 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the…

Sound · Computer Science 2019-04-19 Ruihan Yang , Tianyao Chen , Yiyi Zhang , Gus Xia